Explore
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
ctrlrunCTRLRun
Local
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
The execution safety layer for AI agents.
PythonApache-2.0★ 27No key
AtlaSent AI Action Protection for MCP — authorize agent tool calls before they execute (Claude, Cursor, and other MCP hosts).
Node.jsApache-2.0Few starsNo key
MCP server for Zooza — natural language class scheduling, attendance tracking, and booking management for dance schools, language academies, swim schools, sports clubs, and activity franchises. Works
Hosted by authorMIT★ 6No key
Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signatures, Merkle log proofs, independently verifiable by anyone.
Node.jsApache-2.0★ 8No key
BLACK_WALL MCP server — a pre-action risk check your AI agent calls before any irreversible action (send email, move money, run SQL, delete data).
Node.jsMITFew starsNeeds a key
Unreal Engine MCP Server: Control UE5 with Claude & AI Agents. Supports Python and C++ for custom tool development.
SkillApache-2.0★ 145No key
An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the command.
SkillMIT★ 16No key
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action rec
GoApache-2.0★ 931No key
Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README
PythonApache-2.0★ 37No key
Local MCP server that gives any AI agent safe desktop control on Windows, macOS and Linux. Reads the screen as text and structure (accessibility + OCR) and acts by element name, with screenshots as th
SkillMIT★ 404No key
The deliberation & governance layer for autonomous organizations. Built like an institution: verifiable audit log, Sybil-resistant reputation, delegated identity, and metered access over MPP + x402/AT
Hosted by authorApache-2.0★ 3Few starsNo key
Remote approvals, policy checks, and execution evidence for unattended AI agents.
SkillMIT★ 313No key
Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace MCP Server & CLI Tool
PythonMIT★ 3.4kNo key
The AI's hands and eyes on the web - an AI-native browser framework with structured perception, verified self-healing actions, and an MCP server.
Node.jsMIT★ 1Few starsNo key
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit,
SkillMIT★ 12kNo key
PostgreSQL migration linter. Blocks unsafe migrations before merge: 112 rules, the real Postgres parser, lock analysis, auto-fix. CLI, GitHub Action, MCP.
Node.jsMIT★ 9No key
Exposes MCP tools that prove every method, field, label and form pattern against your real metadata before the AI writes code.
Node.jsMIT★ 159No key
Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT
SkillMIT★ 2.4kNo key
joLink lets AI coding agents work like real Java developers—not just write code, but run, debug, and verify their changes for more reliable results.
PythonMIT★ 3Few starsNo key
MCP server providing semantic Java code analysis for AI agents. Built on Eclipse JDT with tools for navigation, refactoring, search, and metrics.
SkillMIT★ 43No key
Open evidence profile for MCP tool actions. Enforce configured tool-call policies and record decisions and observations in offline-verifiable bundles. Optional Linux kernel controls. No hosted backend
SkillMIT★ 13No key
Who stands behind it
